日韩性视频-久久久蜜桃-www中文字幕-在线中文字幕av-亚洲欧美一区二区三区四区-撸久久-香蕉视频一区-久久无码精品丰满人妻-国产高潮av-激情福利社-日韩av网址大全-国产精品久久999-日本五十路在线-性欧美在线-久久99精品波多结衣一区-男女午夜免费视频-黑人极品ⅴideos精品欧美棵-人人妻人人澡人人爽精品欧美一区-日韩一区在线看-欧美a级在线免费观看

歡迎訪問 生活随笔!

生活随笔

當前位置: 首頁 > 编程资源 > 编程问答 >内容正文

编程问答

TF之Transformer:基于tensorflow和Keras框架(特征编码+Tokenizer处理文本+保存模型)针对UCI新闻数据集利用Transformer算法实现新闻文本多分类案例

發布時間:2024/5/14 编程问答 30 豆豆
TF之Transformer:基于tensorflow和Keras框架(特征編碼+Tokenizer處理文本+保存模型)針對UCI新聞數據集利用Transformer算法實現新聞文本多分類案例

目錄

基于tensorflow和Keras框架(特征編碼+Tokenizer處理文本數據+保存模型)針對UCI新聞數據集利用Transformer算法實現新聞文本多分類案例

# 1、定義數據集

# 2、數據預處理

# 2.1、【類別型】特征編碼化

# 3、模型訓練與推理

# 3.1、切分數據集

# 3.2、文本數據再處理

# 配置Tokenizer

# 3.3、模型創建與編譯

# 定義超參數

# 創建Transformer模型

# 編譯模型

# 3.4、模型訓練

# 3.5、評估模型

# T1、模型保存ckpt

# T2、模型保存h5

# 4、模型推理

# T1、加載ckpt的最新的模型參數

# T2、加載h5模型


相關文章
TF之Transformer:基于tensorflow和Keras框架(特征編碼+Tokenizer處理文本數據+保存模型)針對UCI新聞數據集利用Transformer算法實現新聞文本多分類案例
TF之Transformer:基于tensorflow和Keras框架(特征編碼+Tokenizer處理文本數據+保存模型)針對UCI新聞數據集利用Transformer算法實現新聞文本多分類案例實現代碼

基于tensorflow和Keras框架(特征編碼+Tokenizer處理文本數據+保存模型)針對UCI新聞數據集利用Transformer算法實現新聞文本多分類案例

# 1、定義數據集

IDTITLEURLPUBLISHERCATEGORYSTORYHOSTNAMETIMESTAMP
1Fed official says weak data caused by weather, should not slow taperhttp://www.latimes.com/business/money/la-fi-mo-federal-reserve-plosser-stimulus-economy-20140310,0,1312750.story\?track=rssLos Angeles TimesbddUyU0VZz0BRneMioxUPQVP6sIxvMwww.latimes.com1.39447E+12
2Fed's Charles Plosser sees high bar for change in pace of taperinghttp://www.livemint.com/Politics/H2EvwJSK2VE6OF7iK1g3PP/Feds-Charles-Plosser-sees-high-bar-for-change-in-pace-of-ta.htmlLivemintbddUyU0VZz0BRneMioxUPQVP6sIxvMwww.livemint.com1.39447E+12
3US open: Stocks fall after Fed official hints at accelerated taperinghttp://www.ifamagazine.com/news/us-open-stocks-fall-after-fed-official-hints-at-accelerated-tapering-294436IFA MagazinebddUyU0VZz0BRneMioxUPQVP6sIxvMwww.ifamagazine.com1.39447E+12
4Fed risks falling 'behind the curve', Charles Plosser sayshttp://www.ifamagazine.com/news/fed-risks-falling-behind-the-curve-charles-plosser-says-294430IFA MagazinebddUyU0VZz0BRneMioxUPQVP6sIxvMwww.ifamagazine.com1.39447E+12
5Fed's Plosser: Nasty Weather Has Curbed Job Growthhttp://www.moneynews.com/Economy/federal-reserve-charles-plosser-weather-job-growth/2014/03/10/id/557011MoneynewsbddUyU0VZz0BRneMioxUPQVP6sIxvMwww.moneynews.com1.39447E+12
6Plosser: Fed May Have to Accelerate Tapering Pacehttp://www.nasdaq.com/article/plosser-fed-may-have-to-accelerate-tapering-pace-20140310-00371NASDAQbddUyU0VZz0BRneMioxUPQVP6sIxvMwww.nasdaq.com1.39447E+12
7Fed's Plosser: Taper pace may be too slowhttp://www.marketwatch.com/story/feds-plosser-taper-pace-may-be-too-slow-2014-03-10\?reflink=MW_news_stmpMarketWatchbddUyU0VZz0BRneMioxUPQVP6sIxvMwww.marketwatch.com1.39447E+12
8Fed's Plosser expects US unemployment to fall to 6.2% by the end of 2014http://www.fxstreet.com/news/forex-news/article.aspx\?storyid=23285020-b1b5-47ed-a8c4-96124bb91a39FXstreet.combddUyU0VZz0BRneMioxUPQVP6sIxvMwww.fxstreet.com1.39447E+12
9US jobs growth last month hit by weather:Fed President Charles Plosserhttp://economictimes.indiatimes.com/news/international/business/us-jobs-growth-last-month-hit-by-weatherfed-president-charles-plosser/articleshow/31788000.cmsEconomic TimesbddUyU0VZz0BRneMioxUPQVP6sIxvMeconomictimes.indiatimes.com1.39447E+12
10ECB unlikely to end sterilisation of SMP purchases - tradershttp://www.iii.co.uk/news-opinion/reuters/news/152615Interactive InvestorbdPhGU51DcrolUIMxbRm0InaHGA2XMwww.iii.co.uk1.39447E+12
<class 'pandas.core.frame.DataFrame'> RangeIndex: 422419 entries, 0 to 422418 Data columns (total 8 columns):# Column Non-Null Count Dtype --- ------ -------------- ----- 0 ID 422419 non-null int64 1 TITLE 422419 non-null object2 URL 422419 non-null object3 PUBLISHER 422417 non-null object4 CATEGORY 422419 non-null object5 STORY 422419 non-null object6 HOSTNAME 422419 non-null object7 TIMESTAMP 422419 non-null int64 dtypes: int64(2), object(6) memory usage: 25.8+ MB

# 2、數據預處理

# 2.1、【類別型】特征編碼化

num_classes 4 ['b' 't' 'e' 'm'] <class 'pandas.core.frame.DataFrame'> RangeIndex: 422419 entries, 0 to 422418 Data columns (total 9 columns):# Column Non-Null Count Dtype --- ------ -------------- ----- 0 ID 422419 non-null int64 1 TITLE 422419 non-null object2 URL 422419 non-null object3 PUBLISHER 422417 non-null object4 CATEGORY 422419 non-null object5 STORY 422419 non-null object6 HOSTNAME 422419 non-null object7 TIMESTAMP 422419 non-null int64 8 category_id 422419 non-null int64 dtypes: int64(3), object(6) memory usage: 29.0+ MB

# 3、模型訓練與推理

# 3.1、切分數據集

# 3.2、文本數據再處理

# 配置Tokenizer

# 3.3、模型創建與編譯

# 定義超參數

# 創建Transformer模型

# 編譯模型

# 3.4、模型訓練

Epoch 1/5 10561/10561 [==============================] - 10770s 1s/step - loss: 0.3124 - accuracy: 0.8936 - val_loss: 0.2171 - val_accuracy: 0.9253 Epoch 2/5 10561/10561 [==============================] - 10724s 1s/step - loss: 0.1968 - accuracy: 0.9323 - val_loss: 0.1921 - val_accuracy: 0.9334 Epoch 3/53490/10561 [========>.....................] - ETA: 1:48:29 - loss: 0.1757 - accuracy: 0.9388Epoch 1/3 10561/10561 [==============================] - ETA: 0s - loss: 0.3350 - accuracy: 0.8837

# 3.5、評估模型

# T1、模型保存ckpt

# T2、模型保存h5

# 4、模型推理

# T1、加載ckpt的最新的模型參數

# 將輸入文本轉換為數字序列并進行預測 T1、加載ckpt的最新的模型參數-------------------------------------- 1/1 [==============================] - 0s 441ms/step Apple announces new iPhone 13 ('t', 0.98686767) 1/1 [==============================] - 0s 24ms/step Bitcoin reaches all-time high ('b', 0.8688579)

# T2、加載h5模型

# 將輸入文本轉換為數字序列并進行預測 T2、加載h5模型-------------------------------------- 1/1 [==============================] - 0s 498ms/step Apple is expected to launch a new iPhone in September ('e', 0.87868917) 1/1 [==============================] - 0s 16ms/step Apple announces new iPhone 13 ('e', 0.93488216) 1/1 [==============================] - 0s 17ms/step Bitcoin reaches all-time high ('e', 0.93678874)

總結

以上是生活随笔為你收集整理的TF之Transformer:基于tensorflow和Keras框架(特征编码+Tokenizer处理文本+保存模型)针对UCI新闻数据集利用Transformer算法实现新闻文本多分类案例的全部內容,希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯,歡迎將生活随笔推薦給好友。